The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
● works · ● untested / no effect · ● hurts — every rank is measured against a no-skill baseline
untested★9,423→untested★381→untested★64→untested★381→untested★64→untested★64→untested★9,423→untested★381→untested★64→untested★9,423→untested★381→untested★64→untested★64→untested★381→untested★64→untested★64→untested★64→untested★9,423→untested★381→untested★64→untested★144→untested★64→untested★64→untested★64→untested★381→untested★64→untested★64→untested★381→untested★64→untested★381→untested★64→untested★381→untested★381→untested★64→untested★381→untested★64→untested★381→untested★64→untested★9,423→untested★381→untested★64→untested★9,423→untested★381→untested★64→untested★9,423→untested★381→untested★64→untested★9,423→untested★64→untested★381→
Implement GPT from scratchskillEngineeringL2
nanogpt · Learning transformer internals, quick prototyping, or experimenting with variants without framework overhead.
Triage Freshdesk tickets by priorityskillSupportL2
freshdesk-triage · High-volume support queues where manual triage is the bottleneck.
Understand clinical psychology disordersskillL1
clinical-foundations · Clinical practice where empirical assessment beats intuition for reliability and ethical practice.
Preview Denmark statistics tablesskillDataL1
tables · Organizing structured data where tables provide clarity and queryability.
Master core cognitive processesskillL1
cognitive-psychology · Understanding decision-making biases, memory constraints, or attention bottlenecks in system design.
Map child and adult development stagesskillHRL1
developmental-psychology · Designing age-appropriate experiences, understanding delays, or intervening during critical periods.
Tokenize text 1GB in under 20 secondsskillEngineeringL2
huggingface-tokenizers · Fast, parallel tokenization when model-specific vocabularies and special tokens matter.
Generate 10-20 fresh ad angles fastskillMarketingL1
angle-generator · Marketing/comms where the same fact told through different angles reaches different segments.
Design and conduct psychology researchskillDataL1
research-methods-psych · Psychology research where internal/external validity and replicability are non-negotiable.
Build multilingual tokenizers for CJKskillEngineeringL2
sentencepiece · Multilingual models or custom vocabularies where language-agnostic approach beats language-specific tokenizers.
Generate images with crypto micropaymentsskillMarketingL2
nano-banana-blockrun · Generating production-ready images without API keys when you control on-chain payments via USDC micropayments, avoiding vendor lock-in.
Understand influence and group behaviorskillSalesHRL1
social-psychology · Diagnosing why teams conform to poor decisions or explaining how organizational pressure shapes individual behavior beyond rational choice.
Write incident postmortems that teachskillOpsL1
blameless-postmortem · Converting incidents into organization-wide learning while protecting the psychological safety required for honest incident reporting, especially in distributed systems and on-call rotations.
Audit ecosystem version alignmentskillEngineeringL1
ecosystem-alignment · Keeping a custom Claude Code setup in sync with upstream platform updates, preventing drift and discovering new capabilities to adopt.
Find root causes with causal inferenceskillOpsDataL2
rca-causal-inference · Incidents with rich quantitative data where you need defensible, reproducible, mathematical causal claims (not just narrative RCA), especially when distinguishing multiple confounding factors.
Apply five whys and fishbone diagramsskillOpsL1
rca-classical-methods · Linear, single-cause shop-floor incidents (5 Whys), or multi-pathway quality incidents (Fishbone), or safety-critical system design review (FTA/FMEA) where classical techniques have proven power.
Analyze human factors in incidentsskillOpsL1
rca-human-factors · Safety-critical industries (aviation, healthcare, emergency response, nuclear) where understanding why the operator's action was reasonable from their perspective reveals system design flaws to fix.
Patch activations to test causal claimsskillEngineeringL2
pyvene-interventions · guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework
Screen for psychological distress quicklyskillHRL1
distress-screening · screening for nonspecific psychological distress or tracking symptom burden over time
Analyze complex socio-technical failuresskillOpsL2
rca-systems-theoretic · investigating incidents in healthcare, aviation, nuclear, autonomous systems, distributed microservices, or any system where multiple act...
Merge docs and fixes to main without releaseskillEngineeringL1
push · Solving push challenges
Evaluate arguments and spot author biasskillL1
critical-reading · evaluating arguments, identifying bias, assessing source reliability, analyzing rhetoric, or synthesizing across multiple texts on the sa...
Find, evaluate, and cite informationskillL1
information-literacy · conducting research, evaluating sources, navigating digital information environments, teaching research skills, or addressing plagiarism ...
Analyze literary texts and themesskillL1
literary-analysis · interpreting literary texts, analyzing author craft, applying critical lenses, discussing theme and symbolism, or exploring how literary ...
Cancel and debounce async requestsskillEngineeringL1
riverpod-cancel · Flutter apps cancelling requests when user navigates or triggers rapid refreshes.
Teach phonics and decoding skillsskillL1
phonics-decoding · Teaching early literacy and diagnosing reading errors via Running Records.
Build reading comprehension skillsskillL1
reading-comprehension · Teaching comprehension when decoding is automatic and meaning-construction needs scaffolding.
Interpret genetic variantsskillL1
variant-interpretation · Automated clinical variant reporting with ACMG evidence codes.
Develop vocabulary and word skillsskillL1
vocabulary-development · Teaching Tier 2 academic vocabulary when explicit word learning is needed.
Check Ralph Specum statusskillL2
ralph-specum-status · Real-time verification of spectrum analyzer readiness before measurement campaigns.
Verify facts and sourcesskillOpsMarketingL2
data-fidelity · Discovering data quality issues before training to avoid garbage-in-garbage-out.
Build Claude integrationsskillEngineeringProductL2
claude-typescript-sdk · Integrating Claude into TypeScript backends and Node.js scripts.
Avoid Sentry configuration pitfallsskillEngineeringL1
sentry-known-pitfalls · Quick diagnosis of Sentry setup failures and error categorization issues.
Package research into missionsskillOpsEngineeringL2
research-mission-generator · Decomposing business goals into actionable research programs.
Fix PHP type errors automaticallyskillEngineeringL2
phpstan-resolver · Migrating PHP codebases to strict type checking incrementally.
Analyze scientific data and experimentsskillDataL2
data-analysis-sci · When you have raw measurements and need to extract honest conclusions with proper error analysis.
Manage Node dependencies with pnpmskillEngineeringL1
pnpm · Monorepos needing deterministic builds, strict dependency isolation, and centralized version catalogs.
Teach scientific inquiry through earth systemsskillProductL1
earth-life-systems · When you need to design long-term ecological studies or extract causal claims from field observations.
Train safer AI with constitutional methodsskillEngineeringL1
constitutional-ai · When you want safety alignment without human labels and need explainable reasoning in refusals.
Review your changes since last commitskillEngineeringL1
diff-since-my-commit · Code review workflows where you need to see what others changed to your files.
Design controlled experiments correctlyskillDataL1
experimental-design-sci · When you must isolate causal effects and design has constraints (ethics, cost, timescale).
Moderate LLM outputs with LlamaGuardskillEngineeringL2
llamaguard · Production input/output filtering where you need a specialized 7B moderation model instead of general LLM.
Validate PubFi DSL server contractsskillEngineeringL1
pubfi-dsl-server-contract · When you need strict input validation and reject SQL/unknown-field queries server-side.
Contextualize science through its historyskillProductL1
history-philosophy-science · When teaching or designing science curricula and need historical/philosophical grounding.
Add runtime guardrails to LLM appsskillEngineeringL2
nemo-guardrails · When you need stateful conversational guardrails beyond single-turn content moderation.
Protect GitLab branches from changesskillEngineeringL1
gitlab-protected-branches · Multi-team workflows where you must enforce review gates and prevent force-push accidents.
Communicate complex ideas clearlyskillProductivityL1
science-communication · When translating peer-reviewed findings for policy, education, or public audiences.
Detect prompt injection attacksskillEngineeringL2
prompt-guard · When you need lightweight client-side jailbreak detection before sending to LLM.
Run systematic investigations reliablyskillDataL1
scientific-method · When teaching or designing any empirical study and need a repeatable framework.
Make responses actionable with citationsskillProductivityL1
citations · When generating bibliographies and need fast, accurate formatting across styles.